© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1313
    Prev
    Next
    INDEX
    Explanations

    specific programming and technical terms related to regex and string manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets or regular expressions

    np_acts-logits-general · gemini-2.0-flash

    specific subsets or exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ))){
    -0.35
    "])){
    -0.34
    "){
    -0.34
    bidities
    -0.34
    Jereo
    -0.33
    ofada
    -0.33
    '])){
    -0.33
    --){
    -0.33
    }],
    -0.32
    ]))
    -0.32
    POSITIVE LOGITS
    :✨
    0.54
    httphttps
    0.54
    ReusableCell
    0.52
     ProtoMessage
    0.52
    contentLoaded
    0.52
    SpringRunner
    0.52
    どちらも
    0.51
    abestanden
    0.51
     kasarigan
    0.50
     both
    0.49
    Activations Density 1.300%

    No Known Activations